Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Toronto

$46,000.00

Integrating Human and Artificial Intelligence for Better Patient Care

EF 2024-25

Résumé
Artificial Intelligence (AI) technologies are finding many applications in medicine, from the automatic characterization of likely events in the ICU based on physiological measurements to the analysis of medical text to help in clinical documentation to the identification of specific radiological findings from X-rays and MRIs. The recent burgeoning of AI technologies has been enabled by Machine Learning (ML), and more specifically deep learning -- a type of ML that has become possible due to the growth of both data volume and computational power. Broad applications of deep learning and other AI methodologies have shown great promise in the clinical setting -- from more accurate and rapid prediction of outcomes, to clinical decision support, especially in remote or developing areas that can help identify diseases earlier and more precisely, together enabling improvements of time and cost expenditures. However, despite evidence that AI technologies can match, augment or on certain individual tasks even outperform human clinicians, these methods are still not broadly used in healthcare settings. The work of our team aims to enable the translation of AI technologies into clinical use by solving a number of computational issues that precludes their application - from the development of "smarter" machine learning technologies that are able to more accurately predict certain clinical outcomes, to the creation of more effective user interfaces and data visualization technologies that enable better physician decision making, while not biasing them inappropriately. More specifically, the research program is divided into two complementary Activities. In Activity 1 of this proposal we will develop NLP technology to further improve clinical note taking. While our prior work already enables physicians to capture the full visual and audio spectrum of the patient interaction, we will explore NLP techniques to disambiguate clinician and patient speech, map text spoken by clinicians and patients into biomedical entities and develop better methods for summarization of clinical conversations into structured notes. In Activity 2, we will continue to develop novel approaches for working with laparoscopic surgical data, developing approaches to remove biases from predictions of safe/unsafe areas for cuts, and then further work on methodology that would enable the deployment of such systems into remote areas where surgical care is not readily available.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2023-05585
Name nom
Brudno, Michael
Department département
Computer Science
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
46000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1101
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Human health (including medically-related psychological research)
Area of application fr
Santé publique (y compris recherche psychologique liée à la médecine)
Research subject code
2709
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Other computing methods
Research subject fr
Autres méthodes informatiques
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Integrating Human and Artificial Intelligence for Better Patient Care
Keywords
computational medicine; human computer interaction; machine learning; clinical user interfaces; decision support
Application summary
Artificial Intelligence (AI) technologies are finding many applications in medicine, from the automatic characterization of likely events in the ICU based on physiological measurements to the analysis of medical text to help in clinical documentation to the identification of specific radiological findings from X-rays and MRIs. The recent burgeoning of AI technologies has been enabled by Machine Learning (ML), and more specifically deep learning -- a type of ML that has become possible due to the growth of both data volume and computational power. Broad applications of deep learning and other AI methodologies have shown great promise in the clinical setting -- from more accurate and rapid prediction of outcomes, to clinical decision support, especially in remote or developing areas that can help identify diseases earlier and more precisely, together enabling improvements of time and cost expenditures. However, despite evidence that AI technologies can match, augment or on certain individual tasks even outperform human clinicians, these methods are still not broadly used in healthcare settings. The work of our team aims to enable the translation of AI technologies into clinical use by solving a number of computational issues that precludes their application - from the development of "smarter" machine learning technologies that are able to more accurately predict certain clinical outcomes, to the creation of more effective user interfaces and data visualization technologies that enable better physician decision making, while not biasing them inappropriately. More specifically, the research program is divided into two complementary Activities. In Activity 1 of this proposal we will develop NLP technology to further improve clinical note taking. While our prior work already enables physicians to capture the full visual and audio spectrum of the patient interaction, we will explore NLP techniques to disambiguate clinician and patient speech, map text spoken by clinicians and patients into biomedical entities and develop better methods for summarization of clinical conversations into structured notes. In Activity 2, we will continue to develop novel approaches for working with laparoscopic surgical data, developing approaches to remove biases from predictions of safe/unsafe areas for cuts, and then further work on methodology that would enable the deployment of such systems into remote areas where surgical care is not readily available.